Skip to main content

Documentation Index

Fetch the complete documentation index at: https://docs.tesslate.com/llms.txt

Use this file to discover all available pages before exploring further.

Tesslate OpenSail

​
One agent, every model

OpenSail is model-agnostic. Every AI call routes through a LiteLLM proxy, which exposes a unified OpenAI-compatible interface to any supported provider. Switch from Claude to GPT-4 to Qwen to a local Llama without changing a line of agent code.

LiteLLM gateway

Unified proxy across all providers and local inference

Dynamic pricing

Per-token cost fetched live from the proxy and cached 5 minutes

BYOK

Attach your own keys; platform credits are not charged

Self-hosted

Point LiteLLM at Ollama, vLLM, or any OpenAI-compatible endpoint

​
Supported providers

OpenSail ships with first-party support for every major model provider. Any OpenAI-compatible endpoint also works out of the box.
ProviderFlagship models
AnthropicClaude 3.5/4.x family (Opus, Sonnet, Haiku)
OpenAIGPT-4, GPT-4 Turbo, GPT-4o, o-series
DeepSeekDeepSeek V3, R1
MetaLlama 3.1, Llama 3.2, Llama 3.3
MistralMistral Large, Codestral, Mixtral
QwenQwen 2.5, Qwen-Coder, QwQ
GoogleGemini 1.5/2.x Pro, Flash
MoonshotKimi K2 family
MiniMaxMiniMax M-series
Z.AI (ChatGLM)GLM-4 family
xAIGrok
Additional gateways: OpenRouter (100+ models through a single key), Groq (ultra-low latency), Together, Fireworks, Perplexity, Cohere, Bedrock. Any gateway LiteLLM can reach is routable.

​
How routing works

1

Agent sends a request

The tesslate-agent’s LLM adapter calls the LiteLLM proxy with an OpenAI-style chat completion request.
2

Credit check

The check_credits(user, model_name) function runs before the upstream request. If the model is BYOK for this user, the check always passes. Otherwise it verifies sufficient platform credits across all pools.
3

Provider dispatch

LiteLLM looks up the model name, resolves the provider, and dispatches to the correct upstream API using either the platform’s key, your BYOK key (passthrough mode), or a local endpoint.
4

Stream back

The response streams back through the proxy to the agent, token by token, into the chat UI.
5

Cost and usage logged

Post-request, calculate_cost_cents(model, tokens_in, tokens_out) computes the cost using current pricing. deduct_credits subtracts from credit pools in priority order (daily, bundled, signup bonus, purchased). BYOK requests log with is_byok=True and cost zero.

​
BYOK (Bring Your Own Key)

BYOK lets you use your own API keys instead of platform credits. Available on Pro and Ultra tiers.
  • Cost is zero in platform credits
  • No deduction from any credit pool
  • You pay the upstream provider directly on your own account
  • UsageLog is still created for your analytics, with is_byok=True and billed_status="exempt"
  • No platform margin on top
BYOK detection is provider-prefix based. The is_byok_model(model_name) check looks up the model’s provider in BUILTIN_PROVIDERS. If you have a key stored for that provider, the call runs BYOK automatically.

​
Self-hosted models

For air-gapped deployments or latency-sensitive workloads, point LiteLLM at a local inference server.
Ollama runs open-weight models on your hardware with a simple HTTP API. Add an entry to the LiteLLM config pointing at your Ollama host:
model_list:
  - model_name: llama3-local
    litellm_params:
      model: ollama/llama3
      api_base: http://ollama:11434
The model llama3-local now appears in OpenSail’s model selector and routes to your Ollama instance.
Self-hosted inference requires enough VRAM for the model plus concurrent sessions. Plan for batch size and max sequence length. Ollama and vLLM both handle quantization for smaller GPUs.

​
Model selector in chat

Every chat session has a model selector at the top. The menu shows:
  • Models available to your subscription tier
  • BYOK-enabled models (if you have a matching key stored)
  • Self-hosted models (if your LiteLLM config includes them)
  • Cost badges: platform credits or BYOK or self-hosted
Agents can also declare a default model as part of their configuration (see /guides/customizing-agents). Users can override per session unless the agent locks the model.

​
Default models per tier

TierTypical defaultBundled credits (USD equivalent)
FreeFast, low-cost (e.g., Haiku-class, GPT-3.5-class, Qwen-7B-class)0 bundled, 5 daily
BasicMid-tier (Sonnet-class, GPT-4-class)500
ProTop-tier plus BYOK (Opus-class, GPT-4-class, or your own key)2,000
UltraEverything unlocked8,000
Exact model availability is configured in LiteLLM’s team settings. Your admin (or you, if self-hosting) can expose any subset of models to any tier. See /guides/billing for tier pricing details.

​
Model parameters

All LiteLLM-routed calls accept the standard OpenAI-compatible parameters: temperature, max_tokens, top_p, frequency_penalty, presence_penalty, and stop sequences. Agents can override per call; the platform does not impose hard caps beyond what upstream providers enforce. For extended-thinking capable models (Claude 3.7+, o1, o3), agents can pass a thinking budget. The default thinking effort is set via default_thinking_effort in the platform config.

​
Cost management

Use Haiku-class or Qwen-Coder-7B for UI tweaks and simple edits. Save Opus or GPT-4 for reasoning-heavy debugging and architecture. The cost delta is often 10x.
The agent auto-compacts at 80% of the context window using a cheap summarization model (compaction_summary_model). Long runs accrue compaction cost; clearing chat between unrelated tasks saves more.
If you run many hours per day, BYOK pays for itself quickly. No platform margin; you buy at provider list price.
On Pro/Ultra with self-hosted Qwen-Coder or Llama 3.3, you can drive agents at near-zero marginal cost after GPU depreciation. Great for batch workflows and scheduled agents.

​
Troubleshooting

Your tier may not include that model. Check the model selector; greyed-out entries show the minimum tier required. For self-hosted, confirm the model is in the LiteLLM config and the inference server is reachable.
The LiteLLM per-key budget is a $10,000 runaway ceiling, not the real gate. If you hit it unexpectedly, your admin may need to run ensure_budget_headroom(). The real usage gate is your OpenSail credit balance.
Switch to a faster model (Haiku, Flash, or a hosted Qwen-7B). Reduce max_tokens. Clear chat history to shrink input. If self-hosting, check GPU utilization; batched throughput dominates.
Verify the key in the provider’s console. Check it has sufficient balance. Some providers scope keys to specific models; confirm access. Rotate the key in OpenSail Settings.

​
Next steps

API Keys

Set up BYOK model keys and external API keys for agent invocation

Billing

Credit pools, tiers, and how BYOK changes the math

Self-hosting

Run OpenSail on your own infrastructure with local models

Using Agents

Pick the right model mid-session